© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111513
    Prev
    Next
    INDEX
    Explanations

    which i mean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aching
    0.52
     න
    0.52
     ニュー
    0.52
     brains
    0.51
     друзей
    0.50
     حیر
    0.48
     セ
    0.48
     ブルー
    0.47
    ce
    0.46
    nc
    0.46
    POSITIVE LOGITS
    soever
    0.48
     brings
    0.48
     enables
    0.45
     incorporates
    0.44
    
    0.44
    aggio
    0.43
     aligns
    0.42
     culminates
    0.42
     empowers
    0.42
     constitutes
    0.42
    Activations Density 0.000%

    No Known Activations